knitr::opts_chunk$set(
warning = TRUE, # show warnings during codebook generation
message = TRUE, # show messages during codebook generation
error = TRUE, # do not interrupt codebook generation in case of errors,
# usually better for debugging
echo = TRUE # show R code
)
ggplot2::theme_set(ggplot2::theme_bw())
library(rio)
library(labelled)
library(codebook)
##
## Attaching package: 'codebook'
## The following object is masked from 'package:labelled':
##
## to_factor
codebook_data <- import("../data_processing/output_data/full_data/sr_full_data.csv.gz")
var_label(codebook_data) <- list(
observation = "Unique participant ID number.",
sender = "Section of the experiment currently displayed.",
sender_type = "Type of labjs object currently displayed.",
sender_id = "Order of blocks shown from labjs. Underscores separate different components to the block (block_task_trial_item).",
response = "Participant response to the trial.",
response_action = "Keypress used to indicate their response to the trial.",
ended_on = "How the trial ended (timeout, form submit, completion, response).",
duration = "The duration in milliseconds of the entire trial from time shown to time end.",
time_run = "The time in milliseconds from the start of the experiment it took to run (start to display) the trial.",
time_render = "The time in milliseconds from the start of the experiment it took to render (prepare, get ready for) the trial.",
time_show = "The time in milliseconds from the start of the experiment it took to show the trial on the screen to the participant.",
time_end = "The time in milliseconds from the start of the experiment it took to end the current trial.",
time_commit = "The time in milliseconds from the start of the experiment it took to save the current trial.",
timestamp = "The approximate timestamp of the trial in UTC server time.",
time_switch = "The time in milliseconds from the start of the experiment it took to switch between the previous trial and the current trial.",
url_lab = "The lab code for the PSA member that ran the study.",
meta_labjs_version = "The version of labjs used in the study.",
meta_user_agent = "The browser the participant used in the study.",
meta_platform = "The operating system of the computer used in the experiment.",
meta_language = "The default language set for the browser the participant used in the study.",
meta_locale = "The location of the browser the participant used in the study.",
meta_time_zone = "The timezone set for the browser/computer the participant used in the study.",
meta_timezone_offset = "The time zone offset from UTC time.",
meta_screen_width = "The width of the screen in pixels.",
meta_screen_height = "The height of the screen in pixels.",
meta_scroll_height = "The height of the scroll bar.",
meta_scroll_width = "The width of the scroll bar.",
meta_window_inner_width = "The width of the browser window in pixels.",
meta_window_inner_height = "The height of the browser window in pixels.",
meta_device_pixel_ratio = "The ratio of width to height of the screen in pixels.",
meta_labjs_build_flavor = "The version build of the labjs version - usually production.",
meta_labjs_build_commit = "The commit version of the labjs build.",
please_tell_us_your_gender = "A multiple choice option for the gender of the participant. All answer choices were in the target language, but are presented in English equivalents here.",
which_year_were_you_born = "A numeric entry box for the year of birth for the participant.",
please_tell_us_your_education_level = "A multiple choice option for the education level of the participant. All answer choices were in the target language, but are presented in English equivalents here.",
native_language = "An open choice answer box for the native language of the participant.",
dominanthand = "The domininant hand indicated by the participant, which controlled the keys pressed for each answer choice (word or nonword).",
word = "The string of letters/characters shown on the screen for the trial.",
class = "The type of stimuli shown on the screen (word or nonword).",
correct_response = "The correct answer for the trial.",
correct = "A logical variable indicating if the participant got the trial answer correct.",
feedback = "The feedback a participant received during practice trials.",
fix_sender = "The sender_id column in a sortable format. You can sort the data by observation and this column to ensure it is in trial order."
)
metadata(codebook_data)$name <- "Semantic Priming Across Many Languages (Example using Serbian data)"
metadata(codebook_data)$description <- "This dataset contains the raw trial data of the (Example Serbian but applies to any) data collection from the SPAML project. The data is presented here in long format, with each trial representing one row in the data. Please note that the information about the build of the study will only display on the first trial, and the demographic information will only display on the trial that collected this information. You can assume all other rows with the same observation ID are those same build and demographics. Other 'missing' data occurs when a column is not relevant for that trial (i.e., correct will not show for non-word trial pages).
Semantic priming has been studied for nearly 50 years across various experimental manipulations and theoretical frameworks. These studies provide insight into the cognitive underpinnings of semantic representations in both healthy and clinical populations; however, they have suffered from several issues including generally low sample sizes and a lack of diversity in linguistic implementations. Here, we will test the size and the variability of the semantic priming effect across ten languages by creating a large database of semantic priming values, based on an adaptive sampling procedure. Differences in response latencies between related word-pair conditions and unrelated word-pair conditions (i.e., difference score confidence interval is greater than zero) will allow quantifying evidence for semantic priming, whereas improvements in model fit with the addition of a random intercept for language will provide support for variability in semantic priming across languages."
metadata(codebook_data)$identifier <- "https://doi.org/10.5281/zenodo.10888833"
metadata(codebook_data)$creator <- "Erin M. Buchanan"
metadata(codebook_data)$citation <- "Buchanan, E., Cuccolo, K., Heyman, T., Iyer, A., Coles, N., Lewis Jr, N., Peters, K., van Berkel, N., Taylor, J., Van't Veer, A. E., Montefinese, M., Valentine, K. D., Maxwell, N., Türkan, B. N., Williams, G., Oliveros-Chacana, J. C., Röer, J., Fini, C., Acar, O., … Lewis, S. C. (2024). SemanticPriming/SPAML: SPAML v1 Data Release (v1.0.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.10888833"
metadata(codebook_data)$url <- "https://github.com/SemanticPriming/SPAML/releases/"
metadata(codebook_data)$datePublished <- "2024-05-01"
metadata(codebook_data)$temporalCoverage <- "2022-2024"
metadata(codebook_data)$spatialCoverage <- "Online"
codebook(codebook_data)
Dataset name: Semantic Priming Across Many Languages (Example using Serbian data)
This dataset contains the raw trial data of the (Example Serbian but applies to any) data collection from the SPAML project. The data is presented here in long format, with each trial representing one row in the data. Please note that the information about the build of the study will only display on the first trial, and the demographic information will only display on the trial that collected this information. You can assume all other rows with the same observation ID are those same build and demographics. Other ‘missing’ data occurs when a column is not relevant for that trial (i.e., correct will not show for non-word trial pages).
Semantic priming has been studied for nearly 50 years across various experimental manipulations and theoretical frameworks. These studies provide insight into the cognitive underpinnings of semantic representations in both healthy and clinical populations; however, they have suffered from several issues including generally low sample sizes and a lack of diversity in linguistic implementations. Here, we will test the size and the variability of the semantic priming effect across ten languages by creating a large database of semantic priming values, based on an adaptive sampling procedure. Differences in response latencies between related word-pair conditions and unrelated word-pair conditions (i.e., difference score confidence interval is greater than zero) will allow quantifying evidence for semantic priming, whereas improvements in model fit with the addition of a random intercept for language will provide support for variability in semantic priming across languages.
Temporal Coverage: 2022-2024
Spatial Coverage: Online
Citation: Buchanan, E., Cuccolo, K., Heyman, T., Iyer, A., Coles, N., Lewis Jr, N., Peters, K., van Berkel, N., Taylor, J., Van’t Veer, A. E., Montefinese, M., Valentine, K. D., Maxwell, N., Türkan, B. N., Williams, G., Oliveros-Chacana, J. C., Röer, J., Fini, C., Acar, O., … Lewis, S. C. (2024). SemanticPriming/SPAML: SPAML v1 Data Release (v1.0.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.10888833
Identifier: https://doi.org/10.5281/zenodo.10888833
Date published: 2024-05-01
Creator:
| name | value |
|---|---|
| 1 | Erin M. Buchanan |
|
#Variables
Unique participant ID number.
Distribution of values for observation
0 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| observation | Unique participant ID number. | character | 0 | 1 | 790 | 0 | 14 | 14 | 0 |
Section of the experiment currently displayed.
Distribution of values for sender
0 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| sender | Section of the experiment currently displayed. | character | 0 | 1 | 23 | 0 | 5 | 23 | 0 |
Type of labjs object currently displayed.
Distribution of values for sender_type
0 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| sender_type | Type of labjs object currently displayed. | character | 0 | 1 | 6 | 0 | 9 | 13 | 0 |
Order of blocks shown from labjs. Underscores separate different components to the block (block_task_trial_item).
Distribution of values for sender_id
0 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| sender_id | Order of blocks shown from labjs. Underscores separate different components to the block (block_task_trial_item). | character | 0 | 1 | 2469 | 0 | 1 | 9 | 0 |
Participant response to the trial.
Distribution of values for response
1196072 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| response | Participant response to the trial. | character | 1196072 | 0.3220684 | 3 | 0 | 4 | 8 | 0 |
Keypress used to indicate their response to the trial.
Distribution of values for response_action
1197646 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| response_action | Keypress used to indicate their response to the trial. | character | 1197646 | 0.3211763 | 3 | 0 | 11 | 15 | 0 |
How the trial ended (timeout, form submit, completion, response).
Distribution of values for ended_on
6458 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| ended_on | How the trial ended (timeout, form submit, completion, response). | character | 6458 | 0.9963396 | 4 | 0 | 7 | 15 | 0 |
The duration in milliseconds of the entire trial from time shown to time end.
Distribution of values for duration
5286 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| duration | The duration in milliseconds of the entire trial from time shown to time end. | numeric | 5286 | 0.9970039 | -14 | 759 | 1e+08 | 2272.703 | 106107.3 | ▇▁▁▁▁ |
The time in milliseconds from the start of the experiment it took to run (start to display) the trial.
Distribution of values for time_run
5286 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| time_run | The time in milliseconds from the start of the experiment it took to run (start to display) the trial. | numeric | 5286 | 0.9970039 | 93 | 837395 | 1.1e+08 | 1093147 | 4054966 | ▇▁▁▁▁ |
The time in milliseconds from the start of the experiment it took to render (prepare, get ready for) the trial.
Distribution of values for time_render
5286 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| time_render | The time in milliseconds from the start of the experiment it took to render (prepare, get ready for) the trial. | numeric | 5286 | 0.9970039 | 48 | 837392 | 1.1e+08 | 1093148 | 4054967 | ▇▁▁▁▁ |
The time in milliseconds from the start of the experiment it took to show the trial on the screen to the participant.
Distribution of values for time_show
7650 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| time_show | The time in milliseconds from the start of the experiment it took to show the trial on the screen to the participant. | numeric | 7650 | 0.995664 | 111 | 837621 | 1.1e+08 | 1092463 | 4056253 | ▇▁▁▁▁ |
The time in milliseconds from the start of the experiment it took to end the current trial.
Distribution of values for time_end
5286 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| time_end | The time in milliseconds from the start of the experiment it took to end the current trial. | numeric | 5286 | 0.9970039 | 952 | 839385 | 1.1e+08 | 1095460 | 4056361 | ▇▁▁▁▁ |
The time in milliseconds from the start of the experiment it took to save the current trial.
Distribution of values for time_commit
5286 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| time_commit | The time in milliseconds from the start of the experiment it took to save the current trial. | numeric | 5286 | 0.9970039 | 954 | 839388 | 1.1e+08 | 1095462 | 4056361 | ▇▁▁▁▁ |
The approximate timestamp of the trial in UTC server time.
## 1325567 unique, categorical values, so not shown.
5286 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | min | median | max |
|---|---|---|---|---|---|---|---|---|
| timestamp | The approximate timestamp of the trial in UTC server time. | POSIXct | 5286 | 0.9970039 | 1325567 | 2022-12-13 18:19:18.775 | 2023-10-27 13:26:56.013 | 2024-02-13 22:09:46.043 |
The time in milliseconds from the start of the experiment it took to switch between the previous trial and the current trial.
Distribution of values for time_switch
6096 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| time_switch | The time in milliseconds from the start of the experiment it took to switch between the previous trial and the current trial. | numeric | 6096 | 0.9965448 | 956 | 839382 | 1.1e+08 | 1095245 | 4055929 | ▇▁▁▁▁ |
The lab code for the PSA member that ran the study.
Distribution of values for url_lab
5286 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| url_lab | The lab code for the PSA member that ran the study. | character | 5286 | 0.9970039 | 3 | 0 | 2 | 9 | 0 |
The version of labjs used in the study.
Distribution of values for meta_labjs_version
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| meta_labjs_version | The version of labjs used in the study. | character | 1763509 | 0.0004461 | 1 | 0 | 6 | 6 | 0 |
The browser the participant used in the study.
Distribution of values for meta_user_agent
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| meta_user_agent | The browser the participant used in the study. | character | 1763509 | 0.0004461 | 76 | 0 | 67 | 147 | 0 |
The operating system of the computer used in the experiment.
Distribution of values for meta_platform
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| meta_platform | The operating system of the computer used in the experiment. | character | 1763509 | 0.0004461 | 3 | 0 | 5 | 12 | 0 |
The default language set for the browser the participant used in the study.
Distribution of values for meta_language
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| meta_language | The default language set for the browser the participant used in the study. | character | 1763509 | 0.0004461 | 21 | 0 | 2 | 10 | 0 |
The location of the browser the participant used in the study.
Distribution of values for meta_locale
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| meta_locale | The location of the browser the participant used in the study. | character | 1763509 | 0.0004461 | 13 | 0 | 2 | 10 | 0 |
The timezone set for the browser/computer the participant used in the study.
Distribution of values for meta_time_zone
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| meta_time_zone | The timezone set for the browser/computer the participant used in the study. | character | 1763509 | 0.0004461 | 15 | 0 | 3 | 19 | 0 |
The time zone offset from UTC time.
Distribution of values for meta_timezone_offset
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| meta_timezone_offset | The time zone offset from UTC time. | numeric | 1763509 | 0.0004461 | -120 | -60 | 480 | -68.08132 | 50.90283 | ▇▁▁▁▁ |
The width of the screen in pixels.
Distribution of values for meta_screen_width
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| meta_screen_width | The width of the screen in pixels. | numeric | 1763509 | 0.0004461 | 915 | 1536 | 3440 | 1622.333 | 277.2668 | ▃▇▁▁▁ |
The height of the screen in pixels.
Distribution of values for meta_screen_height
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| meta_screen_height | The height of the screen in pixels. | numeric | 1763509 | 0.0004461 | 515 | 864 | 1440 | 922.9492 | 149.7347 | ▁▇▂▅▁ |
The width of the scroll bar.
Distribution of values for meta_scroll_width
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| meta_scroll_width | The width of the scroll bar. | numeric | 1763509 | 0.0004461 | 767 | 1536 | 3440 | 1602.76 | 276.8653 | ▂▇▅▁▁ |
The height of the scroll bar.
Distribution of values for meta_scroll_height
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| meta_scroll_height | The height of the scroll bar. | numeric | 1763509 | 0.0004461 | 407 | 698 | 1281 | 740.77 | 145.6839 | ▂▇▆▁▁ |
The width of the browser window in pixels.
Distribution of values for meta_window_inner_width
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| meta_window_inner_width | The width of the browser window in pixels. | numeric | 1763509 | 0.0004461 | 767 | 1536 | 3440 | 1602.759 | 276.867 | ▂▇▅▁▁ |
The height of the browser window in pixels.
Distribution of values for meta_window_inner_height
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| meta_window_inner_height | The height of the browser window in pixels. | numeric | 1763509 | 0.0004461 | 407 | 746 | 1329 | 786.4816 | 148.8312 | ▁▇▃▂▁ |
The ratio of width to height of the screen in pixels.
Distribution of values for meta_device_pixel_ratio
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| meta_device_pixel_ratio | The ratio of width to height of the screen in pixels. | numeric | 1763509 | 0.0004461 | 0.9 | 1 | 2.2 | 1.126897 | 0.1870828 | ▇▅▁▁▁ |
The version build of the labjs version - usually production.
Distribution of values for meta_labjs_build_flavor
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| meta_labjs_build_flavor | The version build of the labjs version - usually production. | character | 1763509 | 0.0004461 | 1 | 0 | 10 | 10 | 0 |
The commit version of the labjs build.
Distribution of values for meta_labjs_build_commit
1763509 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| meta_labjs_build_commit | The commit version of the labjs build. | character | 1763509 | 0.0004461 | 1 | 0 | 40 | 40 | 0 |
A multiple choice option for the gender of the participant. All answer choices were in the target language, but are presented in English equivalents here.
Distribution of values for please_tell_us_your_gender
1763527 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| please_tell_us_your_gender | A multiple choice option for the gender of the participant. All answer choices were in the target language, but are presented in English equivalents here. | character | 1763527 | 0.0004359 | 4 | 0 | 4 | 6 | 0 |
A numeric entry box for the year of birth for the participant.
Distribution of values for which_year_were_you_born
1763524 missing values.
| name | label | data_type | n_missing | complete_rate | min | median | max | mean | sd | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| which_year_were_you_born | A numeric entry box for the year of birth for the participant. | numeric | 1763524 | 0.0004376 | 1955 | 2003 | 2005 | 1994.333 | 13.9183 | ▁▂▁▁▇ |
A multiple choice option for the education level of the participant. All answer choices were in the target language, but are presented in English equivalents here.
Distribution of values for please_tell_us_your_education_level
1763525 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| please_tell_us_your_education_level | A multiple choice option for the education level of the participant. All answer choices were in the target language, but are presented in English equivalents here. | character | 1763525 | 0.000437 | 6 | 0 | 6 | 21 | 0 |
An open choice answer box for the native language of the participant.
Distribution of values for native_language
1763533 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| native_language | An open choice answer box for the native language of the participant. | character | 1763533 | 0.0004325 | 36 | 0 | 1 | 17 | 0 |
The domininant hand indicated by the participant, which controlled the keys pressed for each answer choice (word or nonword).
Distribution of values for dominanthand
1763524 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| dominanthand | The domininant hand indicated by the participant, which controlled the keys pressed for each answer choice (word or nonword). | character | 1763524 | 0.0004376 | 2 | 0 | 4 | 5 | 0 |
The string of letters/characters shown on the screen for the trial.
Distribution of values for word
20983 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| word | The string of letters/characters shown on the screen for the trial. | character | 20983 | 0.9881069 | 3920 | 0 | 2 | 20 | 0 |
The type of stimuli shown on the screen (word or nonword).
Distribution of values for class
20983 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| class | The type of stimuli shown on the screen (word or nonword). | character | 20983 | 0.9881069 | 2 | 0 | 4 | 7 | 0 |
The correct answer for the trial.
Distribution of values for correct_response
1202698 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| correct_response | The correct answer for the trial. | character | 1202698 | 0.3183128 | 2 | 0 | 4 | 7 | 0 |
A logical variable indicating if the participant got the trial answer correct.
Distribution of values for correct
1204249 missing values.
| name | label | data_type | n_missing | complete_rate | count | mean |
|---|---|---|---|---|---|---|
| correct | A logical variable indicating if the participant got the trial answer correct. | logical | 1204249 | 0.3174337 | TRU: 523230, FAL: 36817 | 0.9342609 |
The feedback a participant received during practice trials.
Distribution of values for feedback
1756673 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| feedback | The feedback a participant received during practice trials. | character | 1756673 | 0.0043207 | 3 | 0 | 6 | 26 | 0 |
The sender_id column in a sortable format. You can sort the data by observation and this column to ensure it is in trial order.
Distribution of values for fix_sender
1193409 missing values.
| name | label | data_type | n_missing | complete_rate | n_unique | empty | min | max | whitespace |
|---|---|---|---|---|---|---|---|---|---|
| fix_sender | The sender_id column in a sortable format. You can sort the data by observation and this column to ensure it is in trial order. | character | 1193409 | 0.3235778 | 800 | 0 | 11 | 11 | 0 |
The following JSON-LD can be found by search engines, if you share this codebook publicly on the web.
{
"name": "Semantic Priming Across Many Languages (Example using Serbian data)",
"description": "This dataset contains the raw trial data of the (Example Serbian but applies to any) data collection from the SPAML project. The data is presented here in long format, with each trial representing one row in the data. Please note that the information about the build of the study will only display on the first trial, and the demographic information will only display on the trial that collected this information. You can assume all other rows with the same observation ID are those same build and demographics. Other 'missing' data occurs when a column is not relevant for that trial (i.e., correct will not show for non-word trial pages). \n\nSemantic priming has been studied for nearly 50 years across various experimental manipulations and theoretical frameworks. These studies provide insight into the cognitive underpinnings of semantic representations in both healthy and clinical populations; however, they have suffered from several issues including generally low sample sizes and a lack of diversity in linguistic implementations. Here, we will test the size and the variability of the semantic priming effect across ten languages by creating a large database of semantic priming values, based on an adaptive sampling procedure. Differences in response latencies between related word-pair conditions and unrelated word-pair conditions (i.e., difference score confidence interval is greater than zero) will allow quantifying evidence for semantic priming, whereas improvements in model fit with the addition of a random intercept for language will provide support for variability in semantic priming across languages.\n\n\n## Table of variables\nThis table contains variable names, labels, and number of missing values.\nSee the complete codebook for more.\n\n[truncated]\n\n### Note\nThis dataset was automatically described using the [codebook R package](https://rubenarslan.github.io/codebook/) (version 0.9.2).",
"identifier": "https://doi.org/10.5281/zenodo.10888833",
"creator": "Erin M. Buchanan",
"citation": "Buchanan, E., Cuccolo, K., Heyman, T., Iyer, A., Coles, N., Lewis Jr, N., Peters, K., van Berkel, N., Taylor, J., Van't Veer, A. E., Montefinese, M., Valentine, K. D., Maxwell, N., Türkan, B. N., Williams, G., Oliveros-Chacana, J. C., Röer, J., Fini, C., Acar, O., … Lewis, S. C. (2024). SemanticPriming/SPAML: SPAML v1 Data Release (v1.0.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.10888833",
"url": "https://github.com/SemanticPriming/SPAML/releases/",
"datePublished": "2024-05-01",
"temporalCoverage": "2022-2024",
"spatialCoverage": "Online",
"keywords": ["observation", "sender", "sender_type", "sender_id", "response", "response_action", "ended_on", "duration", "time_run", "time_render", "time_show", "time_end", "time_commit", "timestamp", "time_switch", "url_lab", "meta_labjs_version", "meta_user_agent", "meta_platform", "meta_language", "meta_locale", "meta_time_zone", "meta_timezone_offset", "meta_screen_width", "meta_screen_height", "meta_scroll_width", "meta_scroll_height", "meta_window_inner_width", "meta_window_inner_height", "meta_device_pixel_ratio", "meta_labjs_build_flavor", "meta_labjs_build_commit", "please_tell_us_your_gender", "which_year_were_you_born", "please_tell_us_your_education_level", "native_language", "dominanthand", "word", "class", "correct_response", "correct", "feedback", "fix_sender"],
"@context": "http://schema.org/",
"@type": "Dataset",
"variableMeasured": [
{
"name": "observation",
"description": "Unique participant ID number.",
"@type": "propertyValue"
},
{
"name": "sender",
"description": "Section of the experiment currently displayed.",
"@type": "propertyValue"
},
{
"name": "sender_type",
"description": "Type of labjs object currently displayed.",
"@type": "propertyValue"
},
{
"name": "sender_id",
"description": "Order of blocks shown from labjs. Underscores separate different components to the block (block_task_trial_item).",
"@type": "propertyValue"
},
{
"name": "response",
"description": "Participant response to the trial.",
"@type": "propertyValue"
},
{
"name": "response_action",
"description": "Keypress used to indicate their response to the trial.",
"@type": "propertyValue"
},
{
"name": "ended_on",
"description": "How the trial ended (timeout, form submit, completion, response).",
"@type": "propertyValue"
},
{
"name": "duration",
"description": "The duration in milliseconds of the entire trial from time shown to time end.",
"@type": "propertyValue"
},
{
"name": "time_run",
"description": "The time in milliseconds from the start of the experiment it took to run (start to display) the trial.",
"@type": "propertyValue"
},
{
"name": "time_render",
"description": "The time in milliseconds from the start of the experiment it took to render (prepare, get ready for) the trial.",
"@type": "propertyValue"
},
{
"name": "time_show",
"description": "The time in milliseconds from the start of the experiment it took to show the trial on the screen to the participant.",
"@type": "propertyValue"
},
{
"name": "time_end",
"description": "The time in milliseconds from the start of the experiment it took to end the current trial.",
"@type": "propertyValue"
},
{
"name": "time_commit",
"description": "The time in milliseconds from the start of the experiment it took to save the current trial.",
"@type": "propertyValue"
},
{
"name": "timestamp",
"description": "The approximate timestamp of the trial in UTC server time.",
"@type": "propertyValue"
},
{
"name": "time_switch",
"description": "The time in milliseconds from the start of the experiment it took to switch between the previous trial and the current trial.",
"@type": "propertyValue"
},
{
"name": "url_lab",
"description": "The lab code for the PSA member that ran the study.",
"@type": "propertyValue"
},
{
"name": "meta_labjs_version",
"description": "The version of labjs used in the study.",
"@type": "propertyValue"
},
{
"name": "meta_user_agent",
"description": "The browser the participant used in the study.",
"@type": "propertyValue"
},
{
"name": "meta_platform",
"description": "The operating system of the computer used in the experiment.",
"@type": "propertyValue"
},
{
"name": "meta_language",
"description": "The default language set for the browser the participant used in the study.",
"@type": "propertyValue"
},
{
"name": "meta_locale",
"description": "The location of the browser the participant used in the study.",
"@type": "propertyValue"
},
{
"name": "meta_time_zone",
"description": "The timezone set for the browser/computer the participant used in the study.",
"@type": "propertyValue"
},
{
"name": "meta_timezone_offset",
"description": "The time zone offset from UTC time.",
"@type": "propertyValue"
},
{
"name": "meta_screen_width",
"description": "The width of the screen in pixels.",
"@type": "propertyValue"
},
{
"name": "meta_screen_height",
"description": "The height of the screen in pixels.",
"@type": "propertyValue"
},
{
"name": "meta_scroll_width",
"description": "The width of the scroll bar.",
"@type": "propertyValue"
},
{
"name": "meta_scroll_height",
"description": "The height of the scroll bar.",
"@type": "propertyValue"
},
{
"name": "meta_window_inner_width",
"description": "The width of the browser window in pixels.",
"@type": "propertyValue"
},
{
"name": "meta_window_inner_height",
"description": "The height of the browser window in pixels.",
"@type": "propertyValue"
},
{
"name": "meta_device_pixel_ratio",
"description": "The ratio of width to height of the screen in pixels.",
"@type": "propertyValue"
},
{
"name": "meta_labjs_build_flavor",
"description": "The version build of the labjs version - usually production.",
"@type": "propertyValue"
},
{
"name": "meta_labjs_build_commit",
"description": "The commit version of the labjs build.",
"@type": "propertyValue"
},
{
"name": "please_tell_us_your_gender",
"description": "A multiple choice option for the gender of the participant. All answer choices were in the target language, but are presented in English equivalents here.",
"@type": "propertyValue"
},
{
"name": "which_year_were_you_born",
"description": "A numeric entry box for the year of birth for the participant.",
"@type": "propertyValue"
},
{
"name": "please_tell_us_your_education_level",
"description": "A multiple choice option for the education level of the participant. All answer choices were in the target language, but are presented in English equivalents here.",
"@type": "propertyValue"
},
{
"name": "native_language",
"description": "An open choice answer box for the native language of the participant.",
"@type": "propertyValue"
},
{
"name": "dominanthand",
"description": "The domininant hand indicated by the participant, which controlled the keys pressed for each answer choice (word or nonword).",
"@type": "propertyValue"
},
{
"name": "word",
"description": "The string of letters/characters shown on the screen for the trial.",
"@type": "propertyValue"
},
{
"name": "class",
"description": "The type of stimuli shown on the screen (word or nonword).",
"@type": "propertyValue"
},
{
"name": "correct_response",
"description": "The correct answer for the trial.",
"@type": "propertyValue"
},
{
"name": "correct",
"description": "A logical variable indicating if the participant got the trial answer correct.",
"@type": "propertyValue"
},
{
"name": "feedback",
"description": "The feedback a participant received during practice trials.",
"@type": "propertyValue"
},
{
"name": "fix_sender",
"description": "The sender_id column in a sortable format. You can sort the data by observation and this column to ensure it is in trial order.",
"@type": "propertyValue"
}
]
}`